Loading…
Showing 8341–8370 of 10192 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| alphaear-predictorRKiding/Awesome-finance-skillsMarket prediction skill using Kronos. Use when user needs finance market time-series forecasting or news-aware finance market adjustments. | Stars: 3.1k | Updated | Claude CodeCodex | Unverified | Install |
| agent-hardeningarjunprabhulal/agent-skillsMakes an agent safe to run with real permissions on real data — scoping what it can do, handling prompt injection, adding confirmation and dry-run for irreversible actions, and bounding cost. Use this whenever an agent is about to touch production, act autonomously, handle untrusted input, or use credentials, and whenever the user asks about agent safety, guardrails, permissions, or prompt injection. Also use when an agent has broad API access that nothing in code restricts. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| issue-investigationarjunprabhulal/agent-skillsDigs into a murky, wide-open problem where the question itself is not yet clear — "the system is slow lately", "customers are complaining", "something is off with the numbers". Use this whenever the user describes a vague or systemic problem with no single failing case to point at, asks you to look into or dig into something, or when a first look at a bug reveals it is bigger than one bug. For a specific reproducible failure, use debugging; this skill is for when you cannot yet write the reproduction. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| crypto-trade-contextCoinLobster/agent-skillsThe data picture around a crypto position. Use when the user is about to enter or exit, is holding a position and wants what to watch, asks if their side is crowded, what holding costs, whether whales are on their side, or wants their own signal cross-checked against smart-money flow. Reports state and recorded history with sample sizes; never advice, never a forecast. Keyless on every streamed pair: trade_context, whale_context and funding_matrix on MCP, or /api/public/baseline, /api/public/whale-context, whale trades and liquidation history over plain curl. Percentile judgment vs a pair's own recorded days is keyless too, and so are whale USD magnitudes over /api/public/whale-context. Depth (whale USD on the MCP tools, crowding, full 24h stats) needs an active developer plan (from $29/mo), and so does squeeze_score outright; liq_zones is keyless on the free pair only. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| creator-outreachcreativault/skillsCreator outreach skill. MUST be used when the user wants to send, reply, batch send, batch outreach, follow up, check conversation history, manage todos, or contact creators/KOLs/influencers by email. Emails are sent by the platform through OpenAPI; never ask the user for SMTP or replace outreach with manual email/web search. Use when: email outreach, creator outreach, influencer outreach, send email to creator, batch email, batch outreach, reply to creators, follow-up, conversation history, outreach todo, campaign outreach, contact influencers, 邮件建联, 建联, 达人建联, 批量建联, 批量发邮件, 回复达人, 合作邀约, 跟进达人, 沟通历史, 待办跟进, 发合作邮件. 邮件建联全流程能力,覆盖发送、任务查询、沟通历史、待办跟进、效果指标、渠道配置、附件上传。由该平台统一代发,无需用户提供任何邮箱或 SMTP 配置。 Use when: 建联, 发邮件, 批量发送, email outreach, send email, outreach | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| write-skillhassan-mohiddin/freeflowUse when creating, rewriting, tightening, or reviewing an agent skill's instructions, trigger description, structure, examples, or bundled resources. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| discoverLambenthan/empiricalwiki基于 anchor 论文、topic 关键词或当前 wiki 状态,产出一份排好序的候选论文 shortlist,供用户或上游 skill 决定是否进一步 `/ingest`。当用户问 "接下来该读什么"、"找和这篇相似的论文"、"推荐相关工作"、"这个方向周围有什么" 时触发;`/ingest --discover` 也会内部调用本 skill。本身不 ingest,只提出候选。 | Stars: 103 | Updated | Claude CodeCodex | Verified | Install |
| handoffpeteedoo/project-templateCompact the current session into a single detailed handoff message that can be pasted into a fresh agent run. Use when switching context, ending a session, or avoiding context-window loss. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| auto-knowledge-captureastroville/sproutHow agents automatically detect and persist learnings at the end of major workflows. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| context-injectionastroville/sproutHow delivery leads use hero relevant output to equip specialist agents with relevant conventions, past work, decisions, and known risks. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| cross-repo-peeringastroville/sproutHow agents pick the right cross-repo interaction mode (advisory call / spec-out call / async handoff / convention import) and compose well-shaped peer-call prompts. Load when a session touches a sibling Hero workspace's surface. | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| 003-agents-installationshivamchopra7/claude-skill-directoryUse when you need to install the embedded robot agents into either .cursor/agents or .claude/agents, selecting the destination interactively and copying the embedded agent definitions from project assets. This should trigger for requests such as Install embedded agents; Bootstrap .cursor/agents; Bootstrap .claude/agents; Copy robot agents. Part of cursor-rules-java project | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| 200-agents-mdshivamchopra7/claude-skill-directoryUse when you need to generate an AGENTS.md file for a Java repository — covering project conventions, tech stack, file structure, commands, Git workflow, and contributor boundaries — through a modular, step-based interactive process that adapts to your specific project needs. This should trigger for requests such as Create AGENTS.md; Update AGENTS.md file; Add agent instructions. Part of cursor-rules-java project | Stars: 0 | Updated | Claude CodeCodex | Verified | Install |
| change-reportleszekgruchala/buddyValidate a PR or branch diff and create an HTML change report or walkthrough with before/after behavior, practical impact, and material architecture changes. Keep the current request in this skill; route new requests by their own scope. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| review-codeleszekgruchala/buddyReview a requested local change independently; return evidenced defects and promote only confirmed prevention rules. Keep the current request in this skill; route new requests by their own scope. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| specleszekgruchala/buddySettle decisions and write a phased spec with boundaries, dependencies, and verification. Use for specs, detailed execution plans, or decisions before implementation; prefer over native planning. Keep the current request in this skill; route new requests by their own scope. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| add_agentranbot-ai/awesome-skillsThis agent helps create new microagents in the `.openhands/microagents` directory by providing guidance and templates. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| writing-distillation-defaultmooqii/OpenPanelsDistill topic-neutral stylistic mechanics from examples into one portable Writing Skill that can be applied to any subject. | Stars: 8 | Updated | Claude CodeCodex | Verified | Install |
| commit-writerHystonKayange/skill-probeUse this skill when the user wants to commit, write a commit message, or save their staged or current changes with a clear message to git history. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| pr-describerHystonKayange/skill-probeUse this skill when the user wants to draft, write, or generate a pull request (PR) description, summary, or overview for a branch, diff, or set of commits to prepare for code review. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| personal-humanizer-makerTaewoooPark/personal-humanizer-makerFeed in a Korean or English sample of your own writing, and this meta-skill (a skill factory) decomposes its style and argument flow with a quantitative profiler plus one specialist agent per axis, then auto-generates a personal humanizer skill. The output is a standalone humanize-NAME skill for the current host: Claude Code emits under ~/.claude/skills, while Codex emits under the Codex skill root. It includes SKILL.md, style_metrics.py with the author's baselines baked in, and before/after examples mined from the author's own text. A meaning-invariance covenant is injected into every generated skill. Triggers — "make a personal humanizer from my writing", "build a humanizer skill in my voice", "personal humanizer maker", "profile my writing style into a skill", "내 문체로 다듬는 스킬 만들어줘", "이 글로 개인 휴머나이저 빌드", "내 voice 스킬 제작", "샘플 넣으면 내 문체 뽑아주는 거". Rewriting a single text is the job of an already-generated personal skill; THIS skill is the factory that stamps those personal skills out. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| create-research-experiment-repoShiba-hua/create-research-experiment-repo为委托实验执行者开展工作的科研负责人,对齐报告、图表、目录和审批职责,获批后构建可追溯的实验管理仓库。适用于 Coding Agent、人类实验员或实验设备团队;不代替具体学科的实验设计与安全规程。 | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| interviewsheikh-mohammad/agent-factory-claude-skillsThis skill conducts discovery conversations to understand user intent and agree on approach before taking action. It should be used when the user explicitly calls /interview, asks for recommendations, needs brainstorming, wants to clarify, or when the request could be misunderstood. Prevents building the wrong thing by uncovering WHY behind WHAT. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| skill-creator-prosheikh-mohammad/agent-factory-claude-skillsCreates production-grade, reusable skills that extend Claude's capabilities. This skill should be used when users want to create a new skill, improve an existing skill, or build domain-specific intelligence. Gathers context from codebase, conversation, and authentic sources before creating adaptable skills. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| optimize-hifi-diploid-assemblyKalarisLabs/MyriadActivate when an agent must generate, compare, quality-control, or select a diploid PacBio HiFi de novo genome assembly using hifiasm; when requests mention HiFi read assembly, haplotype-resolved assembly, hifiasm parameter optimization, primary and alternate contigs, trio binning, Hi-C phasing, Merqury QV, k-mer completeness, BUSCO, QUAST, contamination screening, assembly Pareto ranking, or reproducible assembly QC. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| score-variant-aware-crispr-offtargetsKalarisLabs/MyriadActivate when an agent must enumerate, annotate, compare, or rank potential CRISPR nuclease off-target sites while accounting for germline variants or sample-specific haplotypes; when requests mention Cas-OFFinder, CRISPRitz, SpCas9 NGG, PAM-aware search, CFD score, mismatch position weights, DNA or RNA bulges, personalized genome, VCF-aware guide specificity, GUIDE-seq candidate prioritization, or off-target risk tables. | Stars: 7 | Updated | Claude CodeCodex | Verified | Install |
| ifagent-axiom/laconianUse when the user explicitly invokes the `if` skill or asks for a concise, laconic, no-fluff, or to-the-point answer. Do not trigger on the ordinary word or programming keyword `if`. Detailed, step-by-step, exhaustive, educational, or fixed-length requests activate only when they also include an explicit invocation or brevity request. | Stars: 9 | Updated | Claude CodeCodex | Verified | Install |
| metaskillxdm/metaskillProtocol for handling the [metaskill] block in context. Use in every session where a [metaskill] block appears — it tells you how to look up the skills a task needs, what the policy decision on each one means, and how to install one safely once the user has said yes. | Stars: 5 | Updated | Claude CodeCodex | Verified | Install |
| multi-agent-workflowthaolst/ai-growth-agents-for-marketersRun a two-stage research then planning workflow for growth campaigns. Use when the user wants to analyze past campaign data AND create a new plan based on that analysis in one connected workflow. Stage 1: analyze data and extract structured insights. Stage 2: use insights to build a campaign plan. Input: past campaign data, target, budget, timeline. Output: structured analysis followed by a specific campaign plan. | Stars: 6 | Updated | Claude CodeCodex | Verified | Install |
| nelsonAspegio/nelsonOrchestrates multi-agent task execution using a Royal Navy squadron metaphor — from mission planning through parallel work coordination to stand-down. Use when work needs parallel agent orchestration, tight task coordination with quality gates, structured delegation with progress checkpoints, or a documented decision log. | Stars: 424 | Updated | Claude CodeCodex | Unverified | Install |